Merge branch 'linus' into x86/urgent, to pick up dependent changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 285 insertions, 97 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 981ff9479648..75f27ee2c263 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
@@ -382,5 +383,7 @@
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 #define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ce4d176b3d13..6b15a24930e0 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -13,14 +13,7 @@
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
 
-#ifdef CONFIG_ISA
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
-#else
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
-#endif
-
 extern int iommu_merge;
-extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
 
 extern const struct dma_map_ops *dma_ops;
@@ -30,7 +23,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-bool arch_dma_alloc_attrs(struct device **dev);
-#define arch_dma_alloc_attrs arch_dma_alloc_attrs
-
 #endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b56d504af654..b774c52e5411 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -10,6 +10,7 @@
 
 #ifndef _ASM_X86_FPU_API_H
 #define _ASM_X86_FPU_API_H
+#include <linux/bottom_half.h>
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
@@ -21,6 +22,36 @@
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
+extern void fpregs_mark_activate(void);
+
+/*
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
+ * A context switch will (and softirq might) save CPU's FPU registers to
+ * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
+ * a random state.
+ */
+static inline void fpregs_lock(void)
+{
+	preempt_disable();
+	local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	local_bh_enable();
+	preempt_enable();
+}
+
+#ifdef CONFIG_X86_DEBUG_FPU
+extern void fpregs_assert_state_consistent(void);
+#else
+static inline void fpregs_assert_state_consistent(void) { }
+#endif
+
+/*
+ * Load the task FPU state before returning to userspace.
+ */
+extern void switch_fpu_return(void);
 
 /*
  * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 745a19d34f23..9e27fa05a7ae 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -14,6 +14,7 @@
 #include <linux/compat.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 #include <asm/user.h>
 #include <asm/fpu/api.h>
@@ -24,14 +25,12 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__initialize(struct fpu *fpu);
 extern void fpu__prepare_read(struct fpu *fpu);
 extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
-extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
 extern void fpu__drop(struct fpu *fpu);
-extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
 extern void fpu__clear(struct fpu *fpu);
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
@@ -122,6 +121,21 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
+#define kernel_insn_err(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
 #define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
@@ -150,6 +164,14 @@ static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 		kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
+static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else
+		return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 {
 	if (IS_ENABLED(CONFIG_X86_32))
@@ -163,6 +185,11 @@ static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
+static inline int copy_kernel_to_fregs_err(struct fregs_state *fx)
+{
+	return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
 {
 	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
@@ -363,6 +390,21 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
 }
 
 /*
+ * Restore xstate from kernel space xsave area, return an error code instead of
+ * an exception.
+ */
+static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+	return err;
+}
+
+/*
  * These must be called with preempt disabled. Returns
  * 'true' if the FPU state is still intact and we can
  * keep registers active.
@@ -487,6 +529,25 @@ static inline void fpregs_activate(struct fpu *fpu)
 }
 
 /*
+ * Internal helper, do not use directly. Use switch_fpu_return() instead.
+ */
+static inline void __fpregs_load_activate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+	int cpu = smp_processor_id();
+
+	if (WARN_ON_ONCE(current->mm == NULL))
+		return;
+
+	if (!fpregs_state_valid(fpu, cpu)) {
+		copy_kernel_to_fpregs(&fpu->state);
+		fpregs_activate(fpu);
+		fpu->last_cpu = cpu;
+	}
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+/*
  * FPU state switching for scheduling.
  *
  * This is a two-stage process:
@@ -494,12 +555,23 @@ static inline void fpregs_activate(struct fpu *fpu)
  *  - switch_fpu_prepare() saves the old state.
  *    This is done within the context of the old process.
  *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
+ *  - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
+ *    will get loaded on return to userspace, or when the kernel needs it.
+ *
+ * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
+ * are saved in the current thread's FPU register state.
+ *
+ * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
+ * hold current()'s FPU registers. It is required to load the
+ * registers before returning to userland or using the content
+ * otherwise.
+ *
+ * The FPU context is only stored/restored for a user task and
+ * ->mm is used to distinguish between kernel and user threads.
  */
 static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
+	if (static_cpu_has(X86_FEATURE_FPU) && current->mm) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
@@ -507,8 +579,7 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		trace_x86_fpu_regs_deactivated(old_fpu);
-	} else
-		old_fpu->last_cpu = -1;
+	}
 }
 
 /*
@@ -516,36 +587,32 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  */
 
 /*
- * Set up the userspace FPU context for the new task, if the task
- * has used the FPU.
+ * Load PKRU from the FPU context if available. Delay loading of the
+ * complete FPU state until the return to userland.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
+static inline void switch_fpu_finish(struct fpu *new_fpu)
 {
-	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->initialized;
+	u32 pkru_val = init_pkru_value;
+	struct pkru_state *pk;
 
-	if (preload) {
-		if (!fpregs_state_valid(new_fpu, cpu))
-			copy_kernel_to_fpregs(&new_fpu->state);
-		fpregs_activate(new_fpu);
-	}
-}
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return;
 
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
 
-	preempt_disable();
-	fpregs_activate(fpu);
-	preempt_enable();
+	/*
+	 * PKRU state is switched eagerly because it needs to be valid before we
+	 * return to userland e.g. for a copy_to_user() operation.
+	 */
+	if (current->mm) {
+		pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
+		if (pk)
+			pkru_val = pk->pkru;
+	}
+	__write_pkru(pkru_val);
 }
 
 /*
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 44bbc39a57b3..7fb516b6893a 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -22,7 +22,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 
 extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
 			      struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
+extern void convert_to_fxsr(struct fxregs_state *fxsave,
 			    const struct user_i387_ia32_struct *env);
 
 unsigned long
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 2e32e178e064..f098f6cab94b 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -294,15 +294,6 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @initialized:
-	 *
-	 * This flag indicates whether this context is initialized: if the task
-	 * is not running then we can restore from this context, if the task
-	 * is running then we should save into this context.
-	 */
-	unsigned char			initialized;
-
-	/*
 	 * @avx512_timestamp:
 	 *
 	 * Records the timestamp of AVX512 use during last context switch.
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 48581988d78c..7e42b285c856 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -2,9 +2,11 @@
 #ifndef __ASM_X86_XSAVE_H
 #define __ASM_X86_XSAVE_H
 
+#include <linux/uaccess.h>
 #include <linux/types.h>
+
 #include <asm/processor.h>
-#include <linux/uaccess.h>
+#include <asm/user.h>
 
 /* Bit 63 of XCR0 is reserved for future expansion */
 #define XFEATURE_MASK_EXTEND	(~(XFEATURE_MASK_FPSSE | (1ULL << 63)))
@@ -46,8 +48,8 @@ extern void __init update_regset_xstate_info(unsigned int size,
 					     u64 xstate_mask);
 
 void fpu__xstate_clear_all_cpu_caps(void);
-void *get_xsave_addr(struct xregs_state *xsave, int xstate);
-const void *get_xsave_field_ptr(int xstate_field);
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+const void *get_xsave_field_ptr(int xfeature_nr);
 int using_compacted_format(void);
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 7469d321f072..f65cfb48cfdd 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -17,8 +17,4 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* _ASM_X86_HUGETLB_H */
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 2bdbbbcfa393..cdf44aa9a501 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0 */
 
 /*
  * This file contains definitions from Hyper-V Hypervisor Top-Level Functional
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 058e40fed167..8a0e56e1dcc9 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -6,6 +6,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/nospec-branch.h>
+
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
 #define __cpuidle __attribute__((__section__(".cpuidle.text")))
 
@@ -54,11 +56,13 @@ static inline void native_irq_enable(void)
 
 static inline __cpuidle void native_safe_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static inline __cpuidle void native_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1378518cf63f..88dd202c8b00 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
+#include <linux/bits.h>
+
 /*
  * CPU model specific register (MSR) numbers.
  *
@@ -40,14 +42,14 @@
 /* Intel MSRs. Some also available on other CPUs */
 
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
-#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
-#define SPEC_CTRL_STIBP			(1 << SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
+#define SPEC_CTRL_STIBP			BIT(SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
 #define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
-#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
+#define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
-#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
 #define MSR_PPIN_CTL			0x0000004e
 #define MSR_PPIN			0x0000004f
@@ -69,20 +71,25 @@
 #define MSR_MTRRcap			0x000000fe
 
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
-#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
-#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
-#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
-#define ARCH_CAP_SSB_NO			(1 << 4)   /*
-						    * Not susceptible to Speculative Store Bypass
-						    * attack, so no Speculative Store Bypass
-						    * control required.
-						    */
+#define ARCH_CAP_RDCL_NO		BIT(0)	/* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		BIT(1)	/* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	BIT(3)	/* Skip L1D flush on vmentry */
+#define ARCH_CAP_SSB_NO			BIT(4)	/*
+						 * Not susceptible to Speculative Store Bypass
+						 * attack, so no Speculative Store Bypass
+						 * control required.
+						 */
+#define ARCH_CAP_MDS_NO			BIT(5)   /*
+						  * Not susceptible to
+						  * Microarchitectural Data
+						  * Sampling (MDS) vulnerabilities.
+						  */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
-#define L1D_FLUSH			(1 << 0)   /*
-						    * Writeback and invalidate the
-						    * L1 data cache.
-						    */
+#define L1D_FLUSH			BIT(0)	/*
+						 * Writeback and invalidate the
+						 * L1 data cache.
+						 */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 39a2fb29378a..eb0f80ce8524 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -6,6 +6,7 @@
 #include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
@@ -40,6 +41,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx,
 
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	/* "mwait %eax, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xc9;"
 		     :: "a" (eax), "c" (ecx));
@@ -74,6 +77,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 			    unsigned long ecx)
 {
+	/* No MDS buffer clear as this is AMD/HYGON only */
+
 	/* "mwaitx %eax, %ebx, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb;"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
@@ -81,6 +86,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	trace_hardirqs_on();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index daf25b60c9e3..109f974f9835 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -308,6 +308,56 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+
+#include <asm/segment.h>
+
+/**
+ * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * This uses the otherwise unused and obsolete VERW instruction in
+ * combination with microcode which triggers a CPU buffer flush when the
+ * instruction is executed.
+ */
+static inline void mds_clear_cpu_buffers(void)
+{
+	static const u16 ds = __KERNEL_DS;
+
+	/*
+	 * Has to be the memory-operand variant because only that
+	 * guarantees the CPU buffer flush functionality according to
+	 * documentation. The register-operand variant does not.
+	 * Works with any segment selector, but a valid writable
+	 * data segment is the fastest variant.
+	 *
+	 * "cc" clobber is required because VERW modifies ZF.
+	 */
+	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
+}
+
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+}
+
+/**
+ * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_idle_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_idle_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3a221942f805..5e0509b41986 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -23,6 +23,8 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/api.h>
 
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
@@ -127,14 +129,29 @@ static inline int pte_dirty(pte_t pte)
 static inline u32 read_pkru(void)
 {
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
-		return __read_pkru();
+		return rdpkru();
 	return 0;
 }
 
 static inline void write_pkru(u32 pkru)
 {
-	if (boot_cpu_has(X86_FEATURE_OSPKE))
-		__write_pkru(pkru);
+	struct pkru_state *pk;
+
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return;
+
+	pk = get_xsave_addr(&current->thread.fpu.state.xsave, XFEATURE_PKRU);
+
+	/*
+	 * The PKRU value in xstate needs to be in sync with the value that is
+	 * written to the CPU. The FPU restore on return to userland would
+	 * otherwise load the previous value again.
+	 */
+	fpregs_lock();
+	if (pk)
+		pk->pkru = pkru;
+	__write_pkru(pkru);
+	fpregs_unlock();
 }
 
 static inline int pte_young(pte_t pte)
@@ -1358,6 +1375,12 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
 #define PKRU_WD_BIT 0x2
 #define PKRU_BITS_PER_PKEY 2
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+extern u32 init_pkru_value;
+#else
+#define init_pkru_value	0
+#endif
+
 static inline bool __pkru_allows_read(u32 pkru, u16 pkey)
 {
 	int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7e99ef67bff0..c34a35c78618 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -978,4 +978,10 @@ enum l1tf_mitigations {
 
 extern enum l1tf_mitigations l1tf_mitigation;
 
+enum mds_mitigations {
+	MDS_MITIGATION_OFF,
+	MDS_MITIGATION_FULL,
+	MDS_MITIGATION_VMWERV,
+};
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 43c029cdc3fe..0a3c4cab39db 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -92,7 +92,7 @@ static inline void native_write_cr8(unsigned long val)
 #endif
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-static inline u32 __read_pkru(void)
+static inline u32 rdpkru(void)
 {
 	u32 ecx = 0;
 	u32 edx, pkru;
@@ -107,7 +107,7 @@ static inline u32 __read_pkru(void)
 	return pkru;
 }
 
-static inline void __write_pkru(u32 pkru)
+static inline void wrpkru(u32 pkru)
 {
 	u32 ecx = 0, edx = 0;
 
@@ -118,8 +118,21 @@ static inline void __write_pkru(u32 pkru)
 	asm volatile(".byte 0x0f,0x01,0xef\n\t"
 		     : : "a" (pkru), "c"(ecx), "d"(edx));
 }
+
+static inline void __write_pkru(u32 pkru)
+{
+	/*
+	 * WRPKRU is relatively expensive compared to RDPKRU.
+	 * Avoid WRPKRU when it would not change the value.
+	 */
+	if (pkru == rdpkru())
+		return;
+
+	wrpkru(pkru);
+}
+
 #else
-static inline u32 __read_pkru(void)
+static inline u32 rdpkru(void)
 {
 	return 0;
 }
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4c305471ec33..b05ad16174e5 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -105,7 +105,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->bx + i, args, n * sizeof(args[0]));
 }
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_I386;
 }
@@ -160,10 +160,12 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	}
 }
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
 	/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
-	return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+	return (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+		task->thread_info.status & TS_COMPAT)
+		? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 }
 #endif	/* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e0eccbcb8447..f9453536f9bb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -88,6 +88,7 @@ struct thread_info {
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING	13	/* pending live patching update */
+#define TIF_NEED_FPU_LOAD	14	/* load FPU on return to userspace */
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
@@ -117,6 +118,7 @@ struct thread_info {
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
+#define _TIF_NEED_FPU_LOAD	(1 << TIF_NEED_FPU_LOAD)
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
index e0e6d7f21399..6b1e87194809 100644
--- a/arch/x86/include/asm/trace/exceptions.h
+++ b/arch/x86/include/asm/trace/exceptions.h
@@ -30,7 +30,7 @@ DECLARE_EVENT_CLASS(x86_exceptions,
 		__entry->error_code = error_code;
 	),
 
-	TP_printk("address=%pf ip=%pf error_code=0x%lx",
+	TP_printk("address=%ps ip=%ps error_code=0x%lx",
 		  (void *)__entry->address, (void *)__entry->ip,
 		  __entry->error_code) );
 
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 069c04be1507..879b77792f94 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -13,22 +13,22 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, initialized)
+		__field(bool, load_fpu)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->initialized	= fpu->initialized;
+		__entry->load_fpu	= test_thread_flag(TIF_NEED_FPU_LOAD);
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->initialized,
+			__entry->load_fpu,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
@@ -64,11 +64,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
 	TP_ARGS(fpu)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
diff --git a/arch/x86/include/uapi/asm/sockios.h b/arch/x86/include/uapi/asm/sockios.h
deleted file mode 100644
index def6d4746ee7..000000000000
--- a/arch/x86/include/uapi/asm/sockios.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sockios.h>